All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mike Rapoport <rppt@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>,
	Andrei Vagin <avagin@google.com>,
	Axel Rasmussen <axelrasmussen@google.com>,
	Baolin Wang <baolin.wang@linux.alibaba.com>,
	David Hildenbrand <david@kernel.org>,
	Harry Yoo <harry.yoo@oracle.com>, Hugh Dickins <hughd@google.com>,
	James Houghton <jthoughton@google.com>,
	"Liam R. Howlett" <Liam.Howlett@oracle.com>,
	"Lorenzo Stoakes (Oracle)" <ljs@kernel.org>,
	"Matthew Wilcox (Oracle)" <willy@infradead.org>,
	Michal Hocko <mhocko@suse.com>, Mike Rapoport <rppt@kernel.org>,
	Muchun Song <muchun.song@linux.dev>,
	Nikita Kalyazin <kalyazin@amazon.com>,
	Oscar Salvador <osalvador@suse.de>,
	Paolo Bonzini <pbonzini@redhat.com>, Peter Xu <peterx@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Shuah Khan <shuah@kernel.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	kvm@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	linux-mm@kvack.org
Subject: [PATCH v3 07/15] userfaultfd: introduce vm_uffd_ops
Date: Mon, 30 Mar 2026 13:11:08 +0300	[thread overview]
Message-ID: <20260330101116.1117699-8-rppt@kernel.org> (raw)
In-Reply-To: <20260330101116.1117699-1-rppt@kernel.org>

From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

Current userfaultfd implementation works only with memory managed by core
MM: anonymous, shmem and hugetlb.

First, there is no fundamental reason to limit userfaultfd support only to
the core memory types and userfaults can be handled similarly to regular
page faults provided a VMA owner implements appropriate callbacks.

Second, historically various code paths were conditioned on
vma_is_anonymous(), vma_is_shmem() and is_vm_hugetlb_page() and some of
these conditions can be expressed as operations implemented by a
particular memory type.

Introduce vm_uffd_ops extension to vm_operations_struct that will delegate
memory type specific operations to a VMA owner.

Operations for anonymous memory are handled internally in userfaultfd
using anon_uffd_ops that implicitly assigned to anonymous VMAs.

Start with a single operation, ->can_userfault() that will verify that a
VMA meets requirements for userfaultfd support at registration time.

Implement that method for anonymous, shmem and hugetlb and move relevant
parts of vma_can_userfault() into the new callbacks.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 include/linux/mm.h            |  5 ++++
 include/linux/userfaultfd_k.h |  6 +++++
 mm/hugetlb.c                  | 15 ++++++++++++
 mm/shmem.c                    | 15 ++++++++++++
 mm/userfaultfd.c              | 44 ++++++++++++++++++++++++-----------
 5 files changed, 72 insertions(+), 13 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index abb4963c1f06..0fbeb8012983 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -741,6 +741,8 @@ struct vm_fault {
 					 */
 };
 
+struct vm_uffd_ops;
+
 /*
  * These are the virtual MM functions - opening of an area, closing and
  * unmapping it (needed to keep files on disk up-to-date etc), pointer
@@ -826,6 +828,9 @@ struct vm_operations_struct {
 	struct page *(*find_normal_page)(struct vm_area_struct *vma,
 					 unsigned long addr);
 #endif /* CONFIG_FIND_NORMAL_PAGE */
+#ifdef CONFIG_USERFAULTFD
+	const struct vm_uffd_ops *uffd_ops;
+#endif
 };
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index a49cf750e803..56e85ab166c7 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -80,6 +80,12 @@ struct userfaultfd_ctx {
 
 extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
 
+/* VMA userfaultfd operations */
+struct vm_uffd_ops {
+	/* Checks if a VMA can support userfaultfd */
+	bool (*can_userfault)(struct vm_area_struct *vma, vm_flags_t vm_flags);
+};
+
 /* A combined operation mode + behavior flags. */
 typedef unsigned int __bitwise uffd_flags_t;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 327eaa4074d3..530bc4337be6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4818,6 +4818,18 @@ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf)
 	return 0;
 }
 
+#ifdef CONFIG_USERFAULTFD
+static bool hugetlb_can_userfault(struct vm_area_struct *vma,
+				  vm_flags_t vm_flags)
+{
+	return true;
+}
+
+static const struct vm_uffd_ops hugetlb_uffd_ops = {
+	.can_userfault = hugetlb_can_userfault,
+};
+#endif
+
 /*
  * When a new function is introduced to vm_operations_struct and added
  * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops.
@@ -4831,6 +4843,9 @@ const struct vm_operations_struct hugetlb_vm_ops = {
 	.close = hugetlb_vm_op_close,
 	.may_split = hugetlb_vm_op_split,
 	.pagesize = hugetlb_vm_op_pagesize,
+#ifdef CONFIG_USERFAULTFD
+	.uffd_ops = &hugetlb_uffd_ops,
+#endif
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct folio *folio,
diff --git a/mm/shmem.c b/mm/shmem.c
index b40f3cd48961..f2a25805b9bf 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3294,6 +3294,15 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd,
 	shmem_inode_unacct_blocks(inode, 1);
 	return ret;
 }
+
+static bool shmem_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
+{
+	return true;
+}
+
+static const struct vm_uffd_ops shmem_uffd_ops = {
+	.can_userfault	= shmem_can_userfault,
+};
 #endif /* CONFIG_USERFAULTFD */
 
 #ifdef CONFIG_TMPFS
@@ -5313,6 +5322,9 @@ static const struct vm_operations_struct shmem_vm_ops = {
 	.set_policy     = shmem_set_policy,
 	.get_policy     = shmem_get_policy,
 #endif
+#ifdef CONFIG_USERFAULTFD
+	.uffd_ops	= &shmem_uffd_ops,
+#endif
 };
 
 static const struct vm_operations_struct shmem_anon_vm_ops = {
@@ -5322,6 +5334,9 @@ static const struct vm_operations_struct shmem_anon_vm_ops = {
 	.set_policy     = shmem_set_policy,
 	.get_policy     = shmem_get_policy,
 #endif
+#ifdef CONFIG_USERFAULTFD
+	.uffd_ops	= &shmem_uffd_ops,
+#endif
 };
 
 int shmem_init_fs_context(struct fs_context *fc)
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index d51e080e9216..e3024a39c19d 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -34,6 +34,25 @@ struct mfill_state {
 	pmd_t *pmd;
 };
 
+static bool anon_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
+{
+	/* anonymous memory does not support MINOR mode */
+	if (vm_flags & VM_UFFD_MINOR)
+		return false;
+	return true;
+}
+
+static const struct vm_uffd_ops anon_uffd_ops = {
+	.can_userfault	= anon_can_userfault,
+};
+
+static const struct vm_uffd_ops *vma_uffd_ops(struct vm_area_struct *vma)
+{
+	if (vma_is_anonymous(vma))
+		return &anon_uffd_ops;
+	return vma->vm_ops ? vma->vm_ops->uffd_ops : NULL;
+}
+
 static __always_inline
 bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
 {
@@ -2021,34 +2040,33 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
 bool vma_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags,
 		       bool wp_async)
 {
-	vm_flags &= __VM_UFFD_FLAGS;
+	const struct vm_uffd_ops *ops = vma_uffd_ops(vma);
 
-	if (vma->vm_flags & VM_DROPPABLE)
-		return false;
-
-	if ((vm_flags & VM_UFFD_MINOR) &&
-	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
-		return false;
+	vm_flags &= __VM_UFFD_FLAGS;
 
 	/*
-	 * If wp async enabled, and WP is the only mode enabled, allow any
+	 * If WP is the only mode enabled and context is wp async, allow any
 	 * memory type.
 	 */
 	if (wp_async && (vm_flags == VM_UFFD_WP))
 		return true;
 
+	/* For any other mode reject VMAs that don't implement vm_uffd_ops */
+	if (!ops)
+		return false;
+
+	if (vma->vm_flags & VM_DROPPABLE)
+		return false;
+
 	/*
 	 * If user requested uffd-wp but not enabled pte markers for
-	 * uffd-wp, then shmem & hugetlbfs are not supported but only
-	 * anonymous.
+	 * uffd-wp, then only anonymous memory is supported
 	 */
 	if (!uffd_supports_wp_marker() && (vm_flags & VM_UFFD_WP) &&
 	    !vma_is_anonymous(vma))
 		return false;
 
-	/* By default, allow any of anon|shmem|hugetlb */
-	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
-	    vma_is_shmem(vma);
+	return ops->can_userfault(vma, vm_flags);
 }
 
 static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
-- 
2.53.0


  parent reply	other threads:[~2026-03-30 10:12 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-30 10:11 [PATCH v3 00/15] mm, kvm: allow uffd support in guest_memfd Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 01/15] userfaultfd: introduce mfill_copy_folio_locked() helper Mike Rapoport
2026-03-31  3:33   ` Harry Yoo (Oracle)
2026-03-30 10:11 ` [PATCH v3 02/15] userfaultfd: introduce struct mfill_state Mike Rapoport
2026-03-31  7:03   ` Harry Yoo (Oracle)
2026-03-31 14:32     ` Mike Rapoport
2026-03-31 15:24       ` Harry Yoo (Oracle)
2026-04-01  7:36         ` Mike Rapoport
2026-04-01 17:37           ` Andrew Morton
2026-04-01 17:44             ` Andrew Morton
2026-04-02  4:36               ` Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 03/15] userfaultfd: introduce mfill_establish_pmd() helper Mike Rapoport
2026-03-31  7:50   ` Harry Yoo (Oracle)
2026-03-30 10:11 ` [PATCH v3 04/15] userfaultfd: introduce mfill_get_vma() and mfill_put_vma() Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 05/15] userfaultfd: retry copying with locks dropped in mfill_atomic_pte_copy() Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 06/15] userfaultfd: move vma_can_userfault out of line Mike Rapoport
2026-03-30 10:11 ` Mike Rapoport [this message]
2026-03-30 16:58   ` [PATCH v3 07/15] userfaultfd: introduce vm_uffd_ops Matthew Wilcox
2026-03-31 11:42     ` Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 08/15] shmem, userfaultfd: use a VMA callback to handle UFFDIO_CONTINUE Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 09/15] userfaultfd: introduce vm_uffd_ops->alloc_folio() Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 10/15] shmem, userfaultfd: implement shmem uffd operations using vm_uffd_ops Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 11/15] userfaultfd: mfill_atomic(): remove retry logic Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 12/15] mm: generalize handling of userfaults in __do_fault() Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 13/15] KVM: guest_memfd: implement userfaultfd operations Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 14/15] KVM: selftests: test userfaultfd minor for guest_memfd Mike Rapoport
2026-03-30 10:11 ` [PATCH v3 15/15] KVM: selftests: test userfaultfd missing " Mike Rapoport
2026-03-30 19:54 ` [PATCH v3 00/15] mm, kvm: allow uffd support in guest_memfd Andrew Morton

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260330101116.1117699-8-rppt@kernel.org \
    --to=rppt@kernel.org \
    --cc=Liam.Howlett@oracle.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=avagin@google.com \
    --cc=axelrasmussen@google.com \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=david@kernel.org \
    --cc=harry.yoo@oracle.com \
    --cc=hughd@google.com \
    --cc=jthoughton@google.com \
    --cc=kalyazin@amazon.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=mhocko@suse.com \
    --cc=muchun.song@linux.dev \
    --cc=osalvador@suse.de \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=seanjc@google.com \
    --cc=shuah@kernel.org \
    --cc=surenb@google.com \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.